{"id":"W4210486131","doi":"10.1109/asru51503.2021.9687877","title":"Hybrid Network with Multi-Level Global-Local Statistics Pooling for Robust Text-Independent Speaker Recognition","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Pooling; NIST; Speech recognition; Speaker recognition; Context (archaeology); Artificial intelligence; Set (abstract data type); Speaker diarisation; Hybrid system; Pattern recognition (psychology); Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000938574,0.0006010835,0.0007138127,0.0002188092,0.0007499218,0.0010702,0.0003517642,0.0002682441,0.0008274872],"category_scores_gemma":[0.0003936173,0.0005942428,0.0002066345,0.0009665541,0.000193846,0.000792545,0.0001303599,0.0003870497,0.0002045372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007081748,"about_ca_system_score_gemma":0.000357952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001865107,"about_ca_topic_score_gemma":0.0004636292,"domain_scores_codex":[0.9957984,0.0003044313,0.0008887651,0.001227865,0.0007803403,0.001000213],"domain_scores_gemma":[0.9967382,0.001231228,0.0004328483,0.0005472868,0.0005966197,0.000453826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007845852,0.000317263,0.00005637707,0.0001921342,0.0003239382,0.0005049088,0.0001680333,0.0002645804,0.00005719338,0.001090525,0.006517045,0.9904295],"study_design_scores_gemma":[0.006788206,0.0002901354,0.0005687224,0.002749562,0.0006008511,0.002985824,0.005418977,0.8475183,0.005804674,0.1245778,0.0005071507,0.00218988],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005572857,0.00018637,0.9889556,0.0007477778,0.001223262,0.0008257079,0.000615287,0.0003931657,0.001480029],"genre_scores_gemma":[0.05073743,0.0003070811,0.9462575,0.001007815,0.0003842754,0.0001280265,0.0006258152,0.00007827095,0.0004737933],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9882396,"threshold_uncertainty_score":0.9999668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1497683730595967,"score_gpt":0.283479670430947,"score_spread":0.1337112973713503,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}